© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109637
    Prev
    Next
    INDEX
    Explanations

    source or origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    も
    -1.45
    <sup>
    -1.27
    <bos>
    -1.27
    ↵
    -1.26
        
    -1.24
     "
    -1.23
     also
    -1.18
         
    -1.18
    ↵↵
    -1.17
     следующие
    -1.16
    POSITIVE LOGITS
     afar
    2.13
     whence
    1.90
     which
    1.80
    Ꮉ
    1.59
     whom
    1.56
    あぁ
    1.55
    って何
    1.55
    さぁ
    1.53
    を変更
    1.50
    にします
    1.48
    Activations Density 0.115%

    No Known Activations